Nonparametric Online Regression while Learning the Metric

Authors: Ilja Kuzborskij, Nicolò Cesa-Bianchi

NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We study algorithms for online nonparametric regression that learn the directions along which the regression function is smoother. Our algorithm learns the Mahalanobis metric based on the gradient outer product matrix G of the regression function (automatically adapting to the effective rank of this matrix), while simultaneously bounding the regret on the same data sequence in terms of the spectrum of G. As a preliminary step in our analysis, we extend a nonparametric online learning algorithm by Hazan and Megiddo enabling it to compete against functions whose Lipschitzness is measured with respect to an arbitrary Mahalanobis metric.
Researcher Affiliation Academia Ilja Kuzborskij EPFL Switzerland ilja.kuzborskij@gmail.comNicol o Cesa-Bianchi Dipartimento di Informatica Universit a degli Studi di Milano Milano 20135, Italy nicolo.cesa-bianchi@unimi.it
Pseudocode Yes Algorithm 1 Nonparametric online regression
Open Source Code No The paper does not provide any specific links or statements about the availability of open-source code for the described methodology.
Open Datasets No The paper focuses on theoretical analysis and does not specify the use of any particular public or open dataset for training. It discusses a theoretical setup where 'instances xt are realizations of i.i.d. random variables Xt drawn according to some fixed and unknown distribution µ'.
Dataset Splits No The paper does not provide specific details on train/validation/test dataset splits, as it is a theoretical work.
Hardware Specification No The paper does not provide any specific details about the hardware used for experiments.
Software Dependencies No The paper does not specify any software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not include concrete details about an experimental setup, such as hyperparameter values or training configurations.